test: 添加全面的测试套件，覆盖所有 Reader 实现

- 测试数量从 83 个增加到 193 个 (+132%)
- 代码覆盖率从 48% 提升到 69% (+44%)
- 为每种文档格式的所有 Reader 实现创建独立测试
- 添加跨 Reader 的一致性验证测试
- 新增 4 个测试规范 (cli-testing, exception-testing, reader-testing, test-fixtures)
- 更新 README 测试统计信息

测试覆盖:
- DOCX: python-docx, markitdown, docling, native-xml, pypandoc, unstructured
- PDF: pypdf, markitdown, docling, docling-ocr, unstructured, unstructured-ocr
- HTML: html2text, markitdown, trafilatura, domscribe
- PPTX: python-pptx, markitdown, docling, native-xml, unstructured
- XLSX: pandas, markitdown, docling, native-xml, unstructured
- CLI: 所有命令行选项和错误处理

所有 193 个测试通过。

tests/test_readers/test_pdf/test_consistency.py

@@ -0,0 +1,41 @@
+"""测试所有 PDF Readers 的一致性。"""
+
+import pytest
+from scripts.readers.pdf import (
+    docling,
+    docling_ocr,
+    markitdown,
+    pypdf,
+    unstructured,
+    unstructured_ocr,
+)
+
+
+class TestPdfReadersConsistency:
+    """验证所有 PDF Readers 解析同一文件时核心文字内容一致。"""
+
+    def test_all_readers_parse_same_content(self, temp_pdf):
+        """测试所有 Readers 解析同一文件时核心内容一致。"""
+        file_path = temp_pdf(text="测试PDF标题\n这是测试段落内容。\n第二段内容。")
+
+        parsers = [
+            ("docling", docling.parse),
+            ("docling_ocr", docling_ocr.parse),
+            ("markitdown", markitdown.parse),
+            ("pypdf", pypdf.parse),
+            ("unstructured", unstructured.parse),
+            ("unstructured_ocr", unstructured_ocr.parse),
+        ]
+
+        successful_results = []
+        for name, parser in parsers:
+            content, error = parser(file_path)
+            if content is not None and content.strip():
+                successful_results.append((name, content))
+
+        assert len(successful_results) > 0, "没有任何 reader 成功解析文件"
+
+        core_texts = ["测试", "PDF", "标题", "段落", "内容"]
+        for name, content in successful_results:
+            assert any(text in content for text in core_texts), \
+                f"{name} 解析结果不包含核心内容"

tests/test_readers/test_pdf/test_docling_ocr_pdf.py

@@ -0,0 +1,44 @@
+"""测试 Docling OCR PDF Reader 的解析功能。"""
+
+import pytest
+from scripts.readers.pdf import docling_ocr
+
+
+class TestDoclingOcrPdfReaderParse:
+    """测试 Docling OCR PDF Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pdf):
+        """测试正常 PDF 文件解析。"""
+        file_path = temp_pdf(text="测试PDF内容\n第二行内容")
+        content, error = docling_ocr.parse(file_path)
+        if content is not None:
+            assert "测试" in content or "PDF" in content or "内容" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pdf")
+        content, error = docling_ocr.parse(non_existent_file)
+        assert content is None
+        assert error is not None
+
+    def test_empty_file(self, temp_pdf):
+        """测试空 PDF 文件。"""
+        file_path = temp_pdf()
+        content, error = docling_ocr.parse(file_path)
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pdf, tmp_path):
+        """测试损坏的 PDF 文件。"""
+        file_path = temp_pdf(text="测试内容")
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content")
+        content, error = docling_ocr.parse(file_path)
+        assert content is None
+        assert error is not None
+
+    def test_special_chars(self, temp_pdf):
+        """测试特殊字符处理。"""
+        file_path = temp_pdf(text="中文测试\nEmoji: 😀\n特殊符号: ©®")
+        content, error = docling_ocr.parse(file_path)
+        if content is not None:
+            assert "中文" in content or "测试" in content

tests/test_readers/test_pdf/test_docling_pdf.py

@@ -0,0 +1,44 @@
+"""测试 Docling PDF Reader 的解析功能。"""
+
+import pytest
+from scripts.readers.pdf import docling
+
+
+class TestDoclingPdfReaderParse:
+    """测试 Docling PDF Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pdf):
+        """测试正常 PDF 文件解析。"""
+        file_path = temp_pdf(text="测试PDF内容\n第二行内容")
+        content, error = docling.parse(file_path)
+        if content is not None:
+            assert "测试" in content or "PDF" in content or "内容" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pdf")
+        content, error = docling.parse(non_existent_file)
+        assert content is None
+        assert error is not None
+
+    def test_empty_file(self, temp_pdf):
+        """测试空 PDF 文件。"""
+        file_path = temp_pdf()
+        content, error = docling.parse(file_path)
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pdf, tmp_path):
+        """测试损坏的 PDF 文件。"""
+        file_path = temp_pdf(text="测试内容")
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content")
+        content, error = docling.parse(file_path)
+        assert content is None
+        assert error is not None
+
+    def test_special_chars(self, temp_pdf):
+        """测试特殊字符处理。"""
+        file_path = temp_pdf(text="中文测试\nEmoji: 😀\n特殊符号: ©®")
+        content, error = docling.parse(file_path)
+        if content is not None:
+            assert "中文" in content or "测试" in content

tests/test_readers/test_pdf/test_markitdown_pdf.py

@@ -0,0 +1,44 @@
+"""测试 MarkItDown PDF Reader 的解析功能。"""
+
+import pytest
+from scripts.readers.pdf import markitdown
+
+
+class TestMarkitdownPdfReaderParse:
+    """测试 MarkItDown PDF Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pdf):
+        """测试正常 PDF 文件解析。"""
+        file_path = temp_pdf(text="测试PDF内容\n第二行内容")
+        content, error = markitdown.parse(file_path)
+        if content is not None:
+            assert "测试" in content or "PDF" in content or "内容" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pdf")
+        content, error = markitdown.parse(non_existent_file)
+        assert content is None
+        assert error is not None
+
+    def test_empty_file(self, temp_pdf):
+        """测试空 PDF 文件。"""
+        file_path = temp_pdf()
+        content, error = markitdown.parse(file_path)
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pdf, tmp_path):
+        """测试损坏的 PDF 文件。"""
+        file_path = temp_pdf(text="测试内容")
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content")
+        content, error = markitdown.parse(file_path)
+        # MarkItDown 可能会尝试解析任何内容
+        assert content is not None or error is not None
+
+    def test_special_chars(self, temp_pdf):
+        """测试特殊字符处理。"""
+        file_path = temp_pdf(text="中文测试\nEmoji: 😀\n特殊符号: ©®")
+        content, error = markitdown.parse(file_path)
+        if content is not None:
+            assert "中文" in content or "测试" in content

tests/test_readers/test_pdf/test_pypdf.py

@@ -0,0 +1,102 @@
+"""测试 pypdf Reader 的解析功能。"""
+
+import pytest
+import os
+from scripts.readers.pdf import PdfReader
+
+
+class TestPypdfReaderParse:
+    """测试 pypdf Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pdf):
+        """测试正常 PDF 文件解析。"""
+        test_text = "这是测试PDF内容\n第二行内容\n第三行内容"
+        file_path = temp_pdf(text=test_text)
+
+        reader = PdfReader()
+        content, failures = reader.parse(file_path)
+
+        # 验证解析成功
+        assert content is not None, f"解析失败: {failures}"
+
+        # 验证关键内容存在（PDF 解析可能有格式差异）
+        assert "测试PDF内容" in content or "测试" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pdf")
+
+        reader = PdfReader()
+        content, failures = reader.parse(non_existent_file)
+
+        # 验证返回 None 和错误信息
+        assert content is None
+        assert len(failures) > 0
+        assert any("不存在" in f or "找不到" in f for f in failures)
+
+    def test_empty_file(self, temp_pdf):
+        """测试空 PDF 文件。"""
+        file_path = temp_pdf(text="")
+
+        reader = PdfReader()
+        content, failures = reader.parse(file_path)
+
+        # 空文件应该返回 None 或空字符串
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pdf):
+        """测试损坏的 PDF 文件。"""
+        # 先创建正常文件
+        file_path = temp_pdf(text="测试内容")
+
+        # 破坏文件内容
+        with open(file_path, "r+b") as f:
+            f.seek(0)
+            f.write(b"corrupted content")
+
+        reader = PdfReader()
+        content, failures = reader.parse(file_path)
+
+        # 验证返回 None 和错误信息
+        assert content is None
+        assert len(failures) > 0
+
+    def test_special_chars(self, temp_pdf):
+        """测试特殊字符处理。"""
+        # PDF 对特殊字符的支持取决于字体
+        # 这里测试基本的中文和英文混合
+        test_text = "中文English混合123"
+        file_path = temp_pdf(text=test_text)
+
+        reader = PdfReader()
+        content, failures = reader.parse(file_path)
+
+        # PDF 解析可能无法完美保留所有字符，只验证部分内容
+        if content:
+            # 至少应该包含一些可识别的内容
+            assert len(content.strip()) > 0
+
+
+class TestPypdfReaderSupports:
+    """测试 pypdf Reader 的 supports 方法。"""
+
+    def test_supports_pdf_extension(self):
+        """测试识别 .pdf 扩展名。"""
+        reader = PdfReader()
+        assert reader.supports("test.pdf") is True
+
+    def test_supports_uppercase_extension(self):
+        """测试识别大写扩展名。"""
+        reader = PdfReader()
+        assert reader.supports("TEST.PDF") is True
+
+    def test_rejects_unsupported_format(self):
+        """测试拒绝不支持的格式。"""
+        reader = PdfReader()
+        assert reader.supports("test.docx") is False
+        assert reader.supports("test.txt") is False
+
+    def test_supports_path_with_spaces(self):
+        """测试包含空格的路径。"""
+        reader = PdfReader()
+        assert reader.supports("path with spaces/test.pdf") is True

tests/test_readers/test_pdf/test_unstructured_ocr_pdf.py

@@ -0,0 +1,44 @@
+"""测试 Unstructured OCR PDF Reader 的解析功能。"""
+
+import pytest
+from scripts.readers.pdf import unstructured_ocr
+
+
+class TestUnstructuredOcrPdfReaderParse:
+    """测试 Unstructured OCR PDF Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pdf):
+        """测试正常 PDF 文件解析。"""
+        file_path = temp_pdf(text="测试PDF内容\n第二行内容")
+        content, error = unstructured_ocr.parse(file_path)
+        if content is not None:
+            assert "测试" in content or "PDF" in content or "内容" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pdf")
+        content, error = unstructured_ocr.parse(non_existent_file)
+        assert content is None
+        assert error is not None
+
+    def test_empty_file(self, temp_pdf):
+        """测试空 PDF 文件。"""
+        file_path = temp_pdf()
+        content, error = unstructured_ocr.parse(file_path)
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pdf, tmp_path):
+        """测试损坏的 PDF 文件。"""
+        file_path = temp_pdf(text="测试内容")
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content")
+        content, error = unstructured_ocr.parse(file_path)
+        assert content is None
+        assert error is not None
+
+    def test_special_chars(self, temp_pdf):
+        """测试特殊字符处理。"""
+        file_path = temp_pdf(text="中文测试\nEmoji: 😀\n特殊符号: ©®")
+        content, error = unstructured_ocr.parse(file_path)
+        if content is not None:
+            assert "中文" in content or "测试" in content

tests/test_readers/test_pdf/test_unstructured_pdf.py

@@ -0,0 +1,44 @@
+"""测试 Unstructured PDF Reader 的解析功能。"""
+
+import pytest
+from scripts.readers.pdf import unstructured
+
+
+class TestUnstructuredPdfReaderParse:
+    """测试 Unstructured PDF Reader 的 parse 方法。"""
+
+    def test_normal_file(self, temp_pdf):
+        """测试正常 PDF 文件解析。"""
+        file_path = temp_pdf(text="测试PDF内容\n第二行内容")
+        content, error = unstructured.parse(file_path)
+        if content is not None:
+            assert "测试" in content or "PDF" in content or "内容" in content
+
+    def test_file_not_exists(self, tmp_path):
+        """测试文件不存在的情况。"""
+        non_existent_file = str(tmp_path / "non_existent.pdf")
+        content, error = unstructured.parse(non_existent_file)
+        assert content is None
+        assert error is not None
+
+    def test_empty_file(self, temp_pdf):
+        """测试空 PDF 文件。"""
+        file_path = temp_pdf()
+        content, error = unstructured.parse(file_path)
+        assert content is None or content.strip() == ""
+
+    def test_corrupted_file(self, temp_pdf, tmp_path):
+        """测试损坏的 PDF 文件。"""
+        file_path = temp_pdf(text="测试内容")
+        with open(file_path, "wb") as f:
+            f.write(b"corrupted content")
+        content, error = unstructured.parse(file_path)
+        assert content is None
+        assert error is not None
+
+    def test_special_chars(self, temp_pdf):
+        """测试特殊字符处理。"""
+        file_path = temp_pdf(text="中文测试\nEmoji: 😀\n特殊符号: ©®")
+        content, error = unstructured.parse(file_path)
+        if content is not None:
+            assert "中文" in content or "测试" in content